CAPSTONE PROJECT - CAR DETECTION

COMPUTER VISION PROJECT- PROJECT BY GROUP 8
Step 1: Import the data
Step 2: Map training and testing images to its classes
Lets visualize few images
a : Train Images
b : Test Images
Step 3: Map training and testing images to its annotations
Lets remane the headings appropriately for the train data!
Lets remane the headings appropriately for the test data!
Now, Lets merge the dataframe of annotations and image dataframe for the train data!
Now, Lets merge the dataframne of annotations and image dataframe for the test data!
Lets have a look at the sanity of the data and take appropriate steps if necessary!
Lets explore the data by plotting few visualizations and performing EDA.
1 : Test data VS Train Data
2 : Cars by year of their origin
3 : Count of top 10
Step 4 : Display images with bounding box
Step 5 : Design, train and test basic CNN models to classify the car

!pip install tensorflow

Model 1
Lets save the Model and Model Weights
Lets analyze the model 1 performance on our Test Data
Let plot the Loss as well as Accuracy for Model 1
Model 2
Lets save the Model and Model Weights
Lets analyze the model 2 performance on our Test Data
Let plot the Loss as well as Accuracy for Model 2
Model 3
Lets save the Model and Model Weights
Lets analyze the model 3 performance on our Test Data
Let plot the Training and Validation Loss as well as Training and Validation Accuracy for Model 3
Lets compare and evaluate the performace of all the 3 CNN models

Insights and Observations :


Model 1:

Model 2:

Model 3:

Overall Assessment:

Methods of Optimization:
Let's now, at last, see how well each of our three models has done in terms of classifying the car photos.
Model 1
Model 2
Model 3
------------End of Project-Milestone 1------------